# Single-step inference

SDXL-Turbo is a fast text-to-image model that generates realistic images from text prompts with just a single network inference, optimized for real-time synthesis.

This is a monocular depth estimation model based on the Apache-2.0 license, suitable for zero-shot depth estimation tasks in wild scenes.

SD-Turbo is a high-speed text-to-image model capable of generating realistic images from text prompts with just a single network inference. Released as a research prototype, it aims to explore compact distilled text-to-image models.

SDXL-Turbo is a fast generative text-to-image model capable of producing realistic images from text prompts through a single network evaluation.